WeatherDiffusion icon indicating copy to clipboard operation
WeatherDiffusion copied to clipboard

Code for "Restoring Vision in Adverse Weather Conditions with Patch-Based Denoising Diffusion Models" [TPAMI 2023]

Results 16 WeatherDiffusion issues
Sort by recently updated
recently updated
newest added

I would like to follow your work, and need the checkpoints to test on new datasets. But there are only checkpoints of $WeatherDiffusion_{64/128}$ while they may perform worse on specific...

Thank you for your patch-based DDM. But I have a question. What's the difference between 'mean estimated noise' and 'mean reconstructed image' during sampling? I think they should be the...

I use python eval_diffusion.py --config "allweather.yml" --resume 'WeatherDiff64.pth.tar' --test_set 'raindrop' --sampling_timesteps 25 --grid_r 16 or 4 python eval_diffusion.py --config "allweather.yml" --resume 'WeatherDiff64.pth.tar' --test_set 'rainfog' --sampling_timesteps 25 --grid_r 16 or 4...

Hi, I don't see a step in your code about calculating the metrics for validation, so how did you choose the best model? Also it takes about 2 minutes to...

is python3.x's question?It always show that my tuple has a TypeError ![QQ截图20240813170913](https://github.com/user-attachments/assets/f0de3148-6366-41dc-b1d1-f4b3747b20e1)

I used two A40 GPUs. It took more than 12 hours to train just over 50 epochs, while the yml file specifies training for 1700+ epochs.